File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1080/23249935.2015.1136008
- Scopus: eid_2-s2.0-84958773153
- WOS: WOS:000371244700003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Predicting crash frequency using an optimised radial basis function neural network model
Title | Predicting crash frequency using an optimised radial basis function neural network model |
---|---|
Authors | |
Keywords | Crash frequency prediction nonlinear relationship radial basis function neural network sensitivity analysis |
Issue Date | 2016 |
Publisher | Taylor & Francis. The Journal's web site is located at http://www.tandfonline.com/loi/ttra21 |
Citation | Transportmetrica A: Transport Science, 2016, v. 12 n. 4, p. 330-345 How to Cite? |
Abstract | With the enormous losses to society that result from highway crashes, gaining a better understanding of the risk factors that affect traffic crash occurrence has long been a prominent focus of safety research. In this study, we develop an optimised radial basis function neural network (RBFNN) model to approximate the nonlinear relationships between crash frequency and the relevant risk factors. Our case study compares the performance of the RBFNN model with that of the traditional negative binomial (NB) and back-propagation neural network (BPNN) models for crash frequency prediction on road segments in Hong Kong. The results indicate that the RBFNN has better fitting and prediction performance than the NB and BPNN models. After the RBFNN is optimised, its approximation performance improves, although several factors are found to hardly influence the frequency of crash occurrence for the crash data that we use. Furthermore, we conduct a sensitivity analysis to determine the effects of the remaining input variables of the optimised RBFNN on the outcome. The results reveal that there are nonlinear relationships between most of the risk factors and crash frequency, and they provide a deeper insight into the risk factors’ effects than the NB model, supporting the use of the modified RBFNN models for road safety analysis. |
Persistent Identifier | http://hdl.handle.net/10722/223845 |
ISSN | 2023 Impact Factor: 3.6 2023 SCImago Journal Rankings: 1.099 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huang, H | - |
dc.contributor.author | Zeng, Q | - |
dc.contributor.author | Pei, X | - |
dc.contributor.author | Wong, SC | - |
dc.contributor.author | Xu, P | - |
dc.date.accessioned | 2016-03-18T02:29:54Z | - |
dc.date.available | 2016-03-18T02:29:54Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | Transportmetrica A: Transport Science, 2016, v. 12 n. 4, p. 330-345 | - |
dc.identifier.issn | 2324-9935 | - |
dc.identifier.uri | http://hdl.handle.net/10722/223845 | - |
dc.description.abstract | With the enormous losses to society that result from highway crashes, gaining a better understanding of the risk factors that affect traffic crash occurrence has long been a prominent focus of safety research. In this study, we develop an optimised radial basis function neural network (RBFNN) model to approximate the nonlinear relationships between crash frequency and the relevant risk factors. Our case study compares the performance of the RBFNN model with that of the traditional negative binomial (NB) and back-propagation neural network (BPNN) models for crash frequency prediction on road segments in Hong Kong. The results indicate that the RBFNN has better fitting and prediction performance than the NB and BPNN models. After the RBFNN is optimised, its approximation performance improves, although several factors are found to hardly influence the frequency of crash occurrence for the crash data that we use. Furthermore, we conduct a sensitivity analysis to determine the effects of the remaining input variables of the optimised RBFNN on the outcome. The results reveal that there are nonlinear relationships between most of the risk factors and crash frequency, and they provide a deeper insight into the risk factors’ effects than the NB model, supporting the use of the modified RBFNN models for road safety analysis. | - |
dc.language | eng | - |
dc.publisher | Taylor & Francis. The Journal's web site is located at http://www.tandfonline.com/loi/ttra21 | - |
dc.relation.ispartof | Transportmetrica A: Transport Science | - |
dc.rights | This is an Accepted Manuscript of an article published by Taylor & Francis in Transportmetrica A: Transport Science on 05 Feb 2016, available online: http://wwww.tandfonline.com/10.1080/23249935.2015.1136008 | - |
dc.subject | Crash frequency prediction | - |
dc.subject | nonlinear relationship | - |
dc.subject | radial basis function neural network | - |
dc.subject | sensitivity analysis | - |
dc.title | Predicting crash frequency using an optimised radial basis function neural network model | - |
dc.type | Article | - |
dc.identifier.email | Wong, SC: hhecwsc@hku.hk | - |
dc.identifier.authority | Wong, SC=rp00191 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1080/23249935.2015.1136008 | - |
dc.identifier.scopus | eid_2-s2.0-84958773153 | - |
dc.identifier.hkuros | 257244 | - |
dc.identifier.volume | 12 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 330 | - |
dc.identifier.epage | 345 | - |
dc.identifier.isi | WOS:000371244700003 | - |
dc.publisher.place | United Kingdom | - |
dc.identifier.issnl | 2324-9935 | - |